Merlin Plus: A Large-Scale, Multi-Cancer, Image-Mask-Report Dataset

2026-09-28

AI Summary

This study addresses the scarcity of cross-organ tumor masks in multi-cancer CT segmentation by constructing the first large-scale longitudinal CT dataset spanning nine organs with radiologist annotations. Methodologically, it introduces a novel report-driven active learning framework that integrates model-assisted pre-annotation with expert review and correction mechanisms, substantially reducing annotation costs while preserving data quality. The resulting dataset provides 1,153 high-quality voxel-level tumor masks alongside extended longitudinal metadata. These resources effectively support cancer progression modeling and facilitate scalable multi-organ tumor detection and longitudinal analysis.

Abstract

Multi-cancer segmentation in computed tomography (CT) is fundamentally limited by the scarcity of tumor masks across different organs. We present Merlin Plus, the first large-scale CT dataset with radiologist-created tumor masks across 9 organs. Merlin Plus extends the Merlin dataset by adding 1,153 per-voxel tumor masks and longitudinal metadata. To create these tumor masks, we developed a report-based active-learning framework in which radiology reports identify tumor cases for annotation and support training of a tumor segmentation model. The model generates initial masks, which radiologists review and correct to produce the final masks, reducing annotation burden while maintaining high-quality annotations. Besides tumor masks, the longitudinal metadata in Merlin Plus enables temporal modeling of cancer progression. By directly addressing the major bottleneck of limited multi-cancer segmentation masks, Merlin Plus supports scalable multi-organ cancer detection, segmentation, and longitudinal analysis in CT. Dataset is available at: https://github.com/MrGiovanni/MerlinPlus

Problem

• multi-cancer segmentation
• computed tomography
• tumor masks
• data scarcity

Innovation

• Multi-cancer segmentation
• Active learning
• Tumor mask annotation
• Longitudinal modeling
• CT dataset